A New Parallel Multi-objective Cooperative Coevolutionary Algorithm Based on SPEA2

Dorronsoro, Bernabé; Cañero, J. Alberto; Danoy, Grégoire; Bouvry, Pascal

Reference : A New Parallel Multi-objective Cooperative Coevolutionary Algorithm Based on SPEA2


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/20796

Title :	A New Parallel Multi-objective Cooperative Coevolutionary Algorithm Based on SPEA2
Language :	English
Author, co-author :	Dorronsoro, Bernabé [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Cañero, J. Alberto [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
	Danoy, Grégoire [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
	Bouvry, Pascal [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
Publication date :	2010
Main document title :	ALIO-INFORMS Joint International Meeting 2010
Pages :	1-2
Peer reviewed :	Yes
On invitation :	No
Audience :	International
Event name :	ALIO-INFORMS Joint International Meeting 2010
Event date :	June 2010
Event place (city) :	Buenos Aires
Event country :	Argentina
Abstract :	[en] We present in this work a new multi-objective cooperative coevolutionary algorithm based on SPEA2 (called CCSPEA2). In this algorithm, we split the solution chromosome into 4 different parts of the same size, and 4 islands are optimizing every single partial solution by using SPEA2. For evaluating the solutions, the islands are sharing their best partial solutions. As a result, CCSPEA2 outperforms SPEA2 in most of tested problems.
Research centres :	University of Luxembourg: High Performance Computing - ULHPC
Permalink :	http://hdl.handle.net/10993/20796

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Limited access	INFORMS_Danoy.pdf		Publisher postprint	2.53 MB	Request a copy

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices